Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Code diffs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DRM
    -0.07
     probing
    -0.07
    .Content
    -0.06
     nhắc
    -0.06
     ajout
    -0.06
     mật
    -0.06
     doz
    -0.06
     Bon
    -0.06
    jištění
    -0.06
     teplot
    -0.06
    POSITIVE LOGITS
    (problem
    0.07
     DEFINE
    0.06
     ภาพ
    0.06
     。↵
    0.06
    ()})↵
    0.06
    FromFile
    0.06
     名無しさん
    0.06
    _socket
    0.06
    <s
    0.06
    _InitStruct
    0.05
    Act Density 0.001%

    No Known Activations